© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33701
    Prev
    Next
    INDEX
    Explanations

    file extension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OSM
    -0.74
     fod
    -0.72
     judi
    -0.69
    旨
    -0.69
     RAB
    -0.66
     SSM
    -0.66
    RAB
    -0.65
     Juliette
    -0.65
     hazards
    -0.65
    ירות
    -0.64
    POSITIVE LOGITS
     PublicKey
    0.78
    piano
    0.75
    owicz
    0.74
     arkadaş
    0.73
    StringUtils
    0.72
    istible
    0.71
    thritis
    0.71
    Francois
    0.71
    nemonic
    0.70
    ᛗ
    0.70
    Activations Density 0.052%

    No Known Activations